How do I install the Prism skill?

Run npx skillmds@latest add cogpros/prism in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Prism safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Prism?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Prism free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

cogpros (@cogpros) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Prism by cogpros — Agent Skill

Name: Prism
Author: cogpros

File contents

PRISM v2 -- Parallel Review by Independent Specialist Models

PRISM uses parallel independent reviewers to surface issues that consensus-based reviews miss. Disagreements are MORE valuable than consensus.

When to Use

Architecture decisions
Security-sensitive changes
Major refactors (>500 lines)
Decisions lasting 6+ months
Open source releases

Skip for: Minor bug fixes, typos, cosmetic changes, urgent hotfixes, easily reversible decisions.

Three Invocation Modes

Mode	Agents	Command
Budget	3 (Security, Performance, DA)	"Budget PRISM"
Standard	6 specialists	"Run PRISM"
Extended	8+ (Standard + Code Reviewers)	"Full PRISM audit"

Six Standard Reviewers

Security Auditor -- Attack vectors, trust boundaries
Performance Analyst -- Metrics, benchmarks, overhead
Simplicity Advocate -- Complexity reduction
Integration Engineer -- Compatibility, migration
Blast Radius Reviewer -- Downstream system effects
Devil's Advocate -- Assumptions, risks, regrets (reviews independently, without prior findings)

How to Execute

Script-based (portable, any agent):

~/.openclaw/scripts/prism.sh --artifact <path> [--mode standard|budget|extended]

Prompts directory: ~/.openclaw/workspace/.claude/skills/prism/prompts/ (12 templates).

In-session (Claude CLI):

Launch 5+ parallel Agent subagents, each with a reviewer persona. Synthesize findings. Archive to analysis/prism/archive/.

Critical Rules

Every finding must cite specific files, line numbers, or command output
Devil's Advocate receives no prior findings brief (independence by design)
Assertions without citations are deprioritized
Disagreements between reviewers often contain the most valuable insights

Dependencies

Script engine: ~/.openclaw/scripts/prism.sh
Shared lib: ~/.openclaw/scripts/lib/review-common.sh
Prompt templates: ~/.openclaw/workspace/.claude/skills/prism/prompts/ (12 files)
Post-review: ~/.openclaw/scripts/sentry-check.sh

Error Recovery

If a reviewer agent fails, synthesis proceeds with remaining reviewers (minimum 3 for valid review)
If prompts directory is missing, verify ~/.openclaw/workspace/.claude/skills/prism/prompts/ exists
If prism.sh exits non-zero, check review-common.sh is sourced correctly

---name: prismdescription: Parallel Review by Independent Specialist Models. Multi-agent review protocol that deploys 5+ specialist reviewers in parallel to eliminate confirmation bias and groupthink.---# PRISM v2 -- Parallel Review by Independent Specialist ModelsPRISM uses parallel independent reviewers to surface issues that consensus-based reviews miss. Disagreements are MORE valuable than consensus.## When to Use- Architecture decisions- Security-sensitive changes- Major refactors (>500 lines)- Decisions lasting 6+ months- Open source releases**Skip for:** Minor bug fixes, typos, cosmetic changes, urgent hotfixes, easily reversible decisions.## Three Invocation Modes| Mode | Agents | Command ||------|--------|---------|| **Budget** | 3 (Security, Performance, DA) | "Budget PRISM" || **Standard** | 6 specialists | "Run PRISM" || **Extended** | 8+ (Standard + Code Reviewers) | "Full PRISM audit" |## Six Standard Reviewers1. **Security Auditor** -- Attack vectors, trust boundaries2. **Performance Analyst** -- Metrics, benchmarks, overhead3. **Simplicity Advocate** -- Complexity reduction4. **Integration Engineer** -- Compatibility, migration5. **Blast Radius Reviewer** -- Downstream system effects6. **Devil's Advocate** -- Assumptions, risks, regrets (reviews independently, without prior findings)## How to Execute### Script-based (portable, any agent):```bash~/.openclaw/scripts/prism.sh --artifact <path> [--mode standard|budget|extended]```Prompts directory: `~/.openclaw/workspace/.claude/skills/prism/prompts/` (12 templates).### In-session (Claude CLI):Launch 5+ parallel Agent subagents, each with a reviewer persona. Synthesize findings. Archive to `analysis/prism/archive/`.## Critical Rules- Every finding must cite specific files, line numbers, or command output- Devil's Advocate receives no prior findings brief (independence by design)- Assertions without citations are deprioritized- Disagreements between reviewers often contain the most valuable insights## Dependencies- Script engine: `~/.openclaw/scripts/prism.sh`- Shared lib: `~/.openclaw/scripts/lib/review-common.sh`- Prompt templates: `~/.openclaw/workspace/.claude/skills/prism/prompts/` (12 files)- Post-review: `~/.openclaw/scripts/sentry-check.sh`## Error Recovery- If a reviewer agent fails, synthesis proceeds with remaining reviewers (minimum 3 for valid review)- If prompts directory is missing, verify `~/.openclaw/workspace/.claude/skills/prism/prompts/` exists- If prism.sh exits non-zero, check review-common.sh is sourced correctly

Frequently asked questions

Prism